Data-Driven Electrolyte Design for Advanced Rechargeable Lithium Batteries

Abstract

The development of high-performance liquid electrolytes is pivotal for advancing rechargeable lithium batteries, which are central to global electrification and renewable energy integration. Conventional electrolyte design, heavily reliant on empirical trial-and-error approaches, faces significant challenges in simultaneously optimizing a complex set of properties, including ionic conductivity, electrochemical stability window, thermal resilience, and most critically, compatibility with electrode interfaces. The efficiency of charge transfer processes and the stability of interphases formed on electrode surfaces, such as the solid electrolyte interphase (SEI) and cathode electrolyte interphase (CEI), are fundamentally governed by electrolyte composition. The nonlinear dependencies among these properties and the vast, unexplored chemical space render traditional methods inefficient. Emerging data-driven strategies represent a paradigm shift, leveraging artificial intelligence (AI) and machine learning (ML) to accelerate the discovery and rational design of next-generation electrolytes. This review comprehensively surveys recent progress in this rapidly evolving field. We begin by systematically outlining the fundamental properties of liquid electrolytes and establishing advanced descriptors for quantifying ion-solvent and ion-anion interactions. The core AI workflow encompassing data acquisition from diverse sources, feature engineering, and the application of various models from supervised learning to generative AI is critically examined. We then showcase the transformative applications of data-driven methodologies, including performance-targeted electrolyte formulation for extreme conditions, prediction of interfacial reaction pathways and SEI/CEI evolution mechanisms, and the development of novel AI algorithms and integrated computational platforms for end-to-end discovery. Despite promising advances, challenges remain, such as data scarcity and standardization, limited model generalizability, and the difficulty of multi-objective optimization balancing performance, safety, and sustainability. By synthesizing these developments and outlining a clear research trajectory, this review aims to provide novel perspectives and inspire continued innovation in the design of high-performance, safe, and sustainable electrolytes, ultimately enabling more reliable and powerful rechargeable lithium batteries for a clean energy future.

Keywords

Electrolytes / Rechargeable lithium batteries / Artificial intelligence / Data driven / Electrode interfaces / Charge transfer

RIGHTS & PERMISSIONS

2025 SIOC, CAS, Shanghai, & WILEY-VCH GmbH